vLLM BlogTools
vLLM x Novita AI: Chord, Faster INT4 MoE for Kimi K2.x. Up to 1.3x on H200, 2.15x on Untuned B300
Novita AI has open-sourced Chord, a high-performance W4A16 MoE CUDA kernel for Kimi K2.x serving shapes, with a Humming-compatible indexed path and grouped SM90 operators.
Read at vLLM Blog ↗Related
ToolsKimi K3 Performance Optimizations in vLLM: The Road to 2.8× Throughput vLLM Blog
ToolsTiered KV Cache Offloading in vLLM vLLM Blog
ToolsGLM 5.3 Optimizations, Part 1: Hybrid HiSparse Offloading in vLLM vLLM Blog

SiliconA Brain Too Big to Carry — On-Device vs Datacenter Inference SemiAnalysis

ToolsCline Desktop: An open-source app for open-weight models Cline Blog
